Machine Learning Engineer and Data Scientist with a background in Financial Mathematics, focused on Machine Learning, Deep Learning, Time Series Forecasting, and Data Science.

I have experience developing end-to-end machine learning solutions, from data preprocessing and feature engineering to model optimization, cross-validation, and performance evaluation. My professional experience also includes financial time-series modeling, quantitative research, algorithmic trading, and backtesting.

• Machine Learning & Deep Learning
• Time Series Forecasting
• Financial Data Analysis
• Feature Engineering & Feature Selection
• Hyperparameter Optimization
• Quantitative Research
• Algorithmic Trading & Backtesting

• Python
• SQL
• Pandas
• NumPy

• Scikit-learn
• XGBoost
• LightGBM
• CatBoost

• TensorFlow
• Keras
• CNN
• LSTM
• GRU

• MySQL
• TA-Lib
• Pandas-TA

• Cross-Validation
• Feature Selection
• RFE
• Hyperparameter Optimization
• Optuna

• Git
• GitHub
• QuantConnect
• Kaggle

Developed and evaluated machine learning and deep learning models for financial time-series analysis and stock price movement prediction.

Focus Areas:

• Time Series Forecasting
• Feature Engineering
• Technical Indicators
• Model Optimization
• Model Evaluation

Models:

• LSTM
• GRU
• CNN
• XGBoost
• LightGBM
• CatBoost

Developed a CNN-based approach for classifying candlestick patterns by transforming OHLCV financial data into image representations using Gramian Angular Field (GAF).

Focus Areas:

• Deep Learning
• Computer Vision
• Time Series
• Financial Data
• CNN
• GAF

Developed and evaluated algorithmic trading strategies through backtesting and forward testing across financial instruments.

Focus Areas:

• Quantitative Research
• Algorithmic Trading
• Backtesting
• Forward Testing
• Strategy Evaluation
• Python

Participated in a multi-class classification competition focused on predicting student health risk.

Improved my public leaderboard score from 0.88 to 0.94963 through iterative model development, feature engineering, model optimization, and ensemble experimentation.

• Final Score: 0.94963
• Final Rank: 1250
• Evaluation Metric: Balanced Accuracy
• Models: CatBoost, LightGBM
• Techniques: Feature Engineering, Cross-Validation, Hyperparameter Tuning, OOF Predictions, Model Blending

Developed a machine learning solution for multi-class stellar classification using CatBoost.

• Public Leaderboard Score: 0.95149
• Model: CatBoost
• Focus Areas: Classification, Feature Engineering, Model Optimization

Kharazmi University

Alzahra University

• Advanced Machine Learning
• Deep Learning
• Computer Vision
• Time Series Forecasting
• Model Optimization
• Machine Learning Engineering

• GitHub:github.com/parastoof
• Kaggle:kaggle.com/prfa9877